Hybrid Human-AI Curriculum Development for Personalised Informal Learning Environments
Project Overview
The document highlights the application of generative AI in education, particularly in creating personalized curricula for informal learning environments. It introduces a prototype curriculum development system that leverages AI and crowdsourcing to tailor educational experiences to individual learners’ needs. This system recommends specific skills, learning topics, and relevant educational materials, thereby facilitating a more dynamic and responsive learning environment. The evaluation of the system demonstrated its effectiveness, achieving high F1-scores in aligning learning goals with appropriate skills and in recommending high-quality educational content. These findings indicate that AI can significantly enhance personalized learning by providing targeted support and resources, ultimately improving educational outcomes and engagement for diverse learners.
Key Applications
AI and Crowdsourcing-Based Curriculum Development System
Context: Personalized informal learning environments targeting a broad audience including learners and educators.
Implementation: Integrated into the eDoer platform, allowing contributors to define high-level learning goals, skills, learning topics, and educational resources with AI recommendations.
Outcomes: Achieved F1-scores of 89% for skill recommendations, 79% for learning topics, and 93% for educational materials.
Challenges: Scalability of personalized education and maintaining the quality of educational content.
Implementation Barriers
Scalability
Educational systems struggle to manage a wide range of learner contexts and requirements in informal environments.
Proposed Solutions: Develop a dynamic curriculum development approach that scales with learner needs and incorporates quality educational content.
User Participation
Crowdsourcing can suffer from low motivation and effectiveness due to the time required from participants.
Proposed Solutions: Improve user engagement by simplifying participation processes and clarifying the benefits of contributions.
Project Team
Mohammadreza Tavakoli
Researcher
Abdolali Faraji
Researcher
Mohammadreza Molavi
Researcher
Stefan T. Mol
Researcher
Gábor Kismihók
Researcher
Contact Information
For information about the paper, please contact the authors.
Authors: Mohammadreza Tavakoli, Abdolali Faraji, Mohammadreza Molavi, Stefan T. Mol, Gábor Kismihók
Source Publication: View Original PaperLink opens in a new window
Project Contact: Dr. Jianhua Yang
LLM Model Version: gpt-4o-mini-2024-07-18
Analysis Provider: Openai